Workshop 1 – Building Interdisciplinary Applications Using Large Language Models.

In this half-day tutorial, we aim to provide experiential training on how to build machine learning pipelines using pre-trained transformer language models for interdisciplinary data science application. We will start with a quick introduction to Python packages (Pytorch, Scipy, scikit-learn) that are heavily used for machine learning projects. In addition, we will cover the domain knowledge behind individual applications. Then, self-supervised deep learning-based large language models (such as Transformers) will be reviewed with a particular focus on computational biology applications. Finally, we will introduce SreamLit for creating web apps, and ollama package for connecting the LLMs.